INDEX

Explanations

references to specific objects and properties

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

----</

-0.52

➟

-0.50

 EnglishChoose

-0.50

Jäh

-0.47

 što

-0.44

endcsname

-0.42

endphp

-0.42

 getopt

-0.42

 koje

-0.41

dung

-0.41

POSITIVE LOGITS

 there

4.40

there

3.46

 THERE

3.10

There

2.77

 There

2.73

THERE

2.64

 thither

2.33

 هناك

2.24

 allí

2.15

 acolo

2.13

Activations Density 1.450%

references to specific objects and properties

No Comments

No Known Activations